Expo orchestrator

Skill Sheshiyer/skill-clusters/skills/expo-orchestrator

Hub-and-spoke agent-skill clusters, one per stack (Astro·GSAP·Remotion, Tauri, …). Installable via skills.sh.

Install

npx -y skills add Sheshiyer/skill-clusters --skill expo-orchestrator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Route an Expo task to the right spoke across the app lifecycle — dev environment (dev client, NativeWind), Expo Router app-building, in-app API routes, native modules, EAS build/submit/update, and SDK upgrades. USE WHEN building or shipping an Expo / React Native app with the Expo toolchain but the specific step isn't named. For RN UI/animation/gesture craft that isn't Expo-specific, hand off to the react-native cluster.

SKILL.md

3.6 KB, 789 tokens by cl100k_base, as published. Nobody here has run it

Expo Orchestrator

Entry skill for the Expo toolchain. It locates the task in the Expo lifecycle (set up → build UI → add native/server → ship via EAS → maintain) and delegates. The platform model — EAS, app config + config plugins, Expo Go vs dev client vs prebuild/CNG, SDK version policy — lives in expo-core; read it before changing native config or upgrading.

Cluster map (routing targets)

expo-core — EAS (Build/Submit/Update/Hosting), app.json/app.config, config plugins, managed↔bare spectrum, SDK versioning.
expo-dev-client — build & distribute a custom dev client (local / TestFlight) beyond Expo Go.
expo-tailwind-setup — Tailwind v4 + NativeWind v5 styling for universal RN.
building-native-ui — building app screens with Expo Router: fundamentals, components, navigation, animations, native tabs.
expo-api-routes — server API routes in Expo Router + EAS Hosting.
expo-module — native modules/views via the Expo Modules API (Swift/Kotlin/TypeScript).
expo-cicd-workflows — CI for EAS (build/submit pipelines).
expo-deployment — release: EAS Build → Submit → Update (OTA).
upgrading-expo — SDK upgrades and dependency alignment.
native-data-fetching — (shared with react-native) fetch/React Query/SWR, caching, offline.

Routing Rules by Intent

Dev environment → expo-dev-client (need native modules / leaving Expo Go), expo-tailwind-setup (styling).
Build screens & navigation → building-native-ui (Expo Router).
In-app backend → expo-api-routes.
Drop to native (Swift/Kotlin) → expo-module.
Ship it → expo-cicd-workflows + expo-deployment (EAS). Confirm the SDK/runtime version first (expo-core).
Data layer → native-data-fetching.
Upgrade SDK → upgrading-expo.
RN craft that isn't Expo-specific (Reanimated, gestures/haptics, pure RN styling/nav, screen design) → react-native cluster (react-native-orchestrator).

Standard Operating Flow

Place the task in the lifecycle (setup → UI → native/server → ship → maintain).
If it touches native config, EAS, or SDK version, pull the model from expo-core first.
Delegate; for "ship" asks, sequence build → submit → update and confirm signing/version.
Return: chosen spoke(s), EAS/config implications, target platform(s), next action.

Guardrails

See expo-core. In short: keep the SDK version the source of truth (it pins the RN version and native deps — don't mix); prefer config plugins over manual native edits so prebuild stays reproducible; confirm credentials/identifiers before an EAS Submit; treat a managed→bare ejection as a one-way decision worth stating.

Loading spokes on demand

To keep CLI startup context lean, this cluster's spokes are not separately registered as skills — only this orchestrator and its *-core are enumerated. When you route to a spoke named above, load it on demand by reading its file:

~/.agents/skill-clusters/skills/<spoke-name>/SKILL.md (or skills/<spoke-name>/SKILL.md inside the skill-clusters repo).

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most agent orchestration skills give in 789 tokens

Counted across 742 of the 995 authors here whose files we hold, read 2026-08-07

reference existing artifacts by path or URLin 53 of 742, across 25 files
run the full test suite after integrating changesin 51 of 742, across 19 files
dispatch one agent per independent problem domainin 50 of 742, across 17 files
verify fixes do not conflictin 45 of 742, across 13 files
include a suggested skills section in the documentin 45 of 742, across 17 files
redact sensitive informationin 41 of 742, across 11 files
save to the temporary directory of the operating systemin 39 of 742, across 10 files
tailor the document to user-provided focus argumentsin 39 of 742, across 9 files
spot check agent changes for systematic errorsin 34 of 742, across 7 files
write a handoff document summarising the current conversationin 31 of 742, across 6 files
Assign each agent a specific scopein 23 of 742, across 8 files
provide specific scope and clear goalin 23 of 742, across 5 files

Said here and by no other author read

place the task in the lifecycle
load the core model before changing native config
load the core model before upgrading SDK
delegate the task to the matched spoke
sequence build, submit, and update for shipping
confirm credentials and identifiers before EAS submit

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.